© 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. 13791
    Prev
    Next
    INDEX
    Explanations

    human speech markers, such as question/answer pairs

    oai_token-act-pair · gemini-2.0-flash

    adjectives expressing excellence

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

    conversational text

    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
    SharedDtor
    -0.42
    +#+#
    -0.41
     
    -0.41
     will
    -0.40
     I
    -0.40
     according
    -0.40
     i
    -0.39
    i
    -0.39
     Here
    -0.37
     Black
    -0.37
    POSITIVE LOGITS
     vectorielle
    0.75
     terrific
    0.74
     vectorielles
    0.73
    WebElementEntity
    0.73
    TacToe
    0.73
    TargetException
    0.72
     wonderful
    0.70
     marvellous
    0.69
     fantastic
    0.69
    BufferException
    0.68
    Activations Density 1.282%

    No Known Activations