© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15342
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of"(8 and 9), "in"(8) and also some variety of seemingly random words and fragments in a few different languages with varying degrees of activation

    oai_token-act-pair · gemini-2.0-flash

    Foreign language phrases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     which
    -2.13
     who
    -1.74
    which
    -1.72
     WHICH
    -1.55
     that
    -1.44
     Which
    -1.43
    Which
    -1.40
     whom
    -1.36
    who
    -1.28
     cui
    -1.09
    POSITIVE LOGITS
     die
    1.38
     som
    1.16
    die
    0.98
     care
    0.93
    Die
    0.90
     Die
    0.87
     DIE
    0.85
    som
    0.80
     Care
    0.74
    Som
    0.70
    Activations Density 1.100%

    No Known Activations