© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8527
    Prev
    Next
    INDEX
    Explanations

    references to Agatha Christie

    oai_token-act-pair · gemini-2.0-flash

    terms related to investigation

    np_token-act-pair-logits · gpt-4o-mini

    investigation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.77
    antMatchers
    -0.57
    jema
    -0.47
    IVEREF
    -0.46
    Ecotoxicity
    -0.45
     setuptools
    -0.45
    הערות
    -0.45
     initWithFrame
    -0.45
    المكان
    -0.45
    ]=>
    -0.43
    POSITIVE LOGITS
     investigation
    1.48
     Investigation
    1.43
     investigations
    1.36
     INVESTIGATION
    1.34
     investigators
    1.34
    Investigation
    1.30
    investig
    1.30
    investigation
    1.29
     investigator
    1.28
     investigating
    1.27
    Activations Density 2.142%

    No Known Activations