© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15077
    Prev
    Next
    INDEX
    Explanations

    code snippets related to data streaming with the through2-map package

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     De
    -0.82
     Ge
    -0.82
     Po
    -0.81
     Di
    -0.81
     Sa
    -0.81
     Mas
    -0.81
     Ar
    -0.80
     Ne
    -0.80
     Par
    -0.79
     Mo
    -0.79
    POSITIVE LOGITS
     purpoſe
    0.47
    seamnă
    0.43
     Majefty
    0.40
     poffible
    0.39
    ſelf
    0.39
     pleaſure
    0.39
     uſed
    0.37
     chofe
    0.37
     Theſe
    0.36
     myſelf
    0.36
    Activations Density 0.949%

    No Known Activations