© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15313
    Prev
    Next
    INDEX
    Explanations

    dialogue involving queens and their subjects

    oai_token-act-pair · gemini-2.0-flash

    firm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ,:);
    -0.64
    ftagPool
    -0.62
     cref
    -0.62
     ModelExpression
    -0.57
    WireFormat
    -0.57
    ')['
    -0.56
    %");
    -0.56
     BoxFit
    -0.56
    odeon
    -0.54
    TagMode
    -0.53
    POSITIVE LOGITS
    Firm
    0.59
    كويكب
    0.57
    +#+
    0.57
     Firm
    0.56
     firmly
    0.54
    #+#
    0.52
    Jegyzetek
    0.49
     berke
    0.48
    ApiModelProperty
    0.47
     firm
    0.47
    Activations Density 1.230%

    No Known Activations