© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13252
    Prev
    Next
    INDEX
    Explanations

    mentions of positive and negative results

    oai_token-act-pair · gemini-2.0-flash

    negative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     negative
    -2.28
    negative
    -2.08
     Negative
    -2.05
    Negative
    -2.05
     positive
    -1.72
    positive
    -1.55
    NEGATIVE
    -1.55
     NEGATIVE
    -1.55
     Positive
    -1.54
    Positive
    -1.51
    POSITIVE LOGITS
    igslist
    0.62
    issage
    0.58
    aglio
    0.57
    orace
    0.55
    DllImport
    0.54
    áte
    0.54
     Resonance
    0.54
     juries
    0.54
     seized
    0.54
     stocking
    0.54
    Activations Density 0.943%

    No Known Activations