© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4131
    Prev
    Next
    INDEX
    Explanations

    positive and complimentary adjectives

    oai_token-act-pair · gemini-2.0-flash

    perfect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    |}{$
    -0.91
     perfect
    -0.88
    ^(@)
    -0.88
     automatiques
    -0.87
     vectoriales
    -0.86
    ".
    -0.85
     vettoriale
    -0.85
    perfect
    -0.84
     perfetta
    -0.84
     Efq
    -0.83
    POSITIVE LOGITS
     i
    0.58
     Assist
    0.56
    Explicación
    0.54
     assist
    0.53
    daad
    0.52
     dinam
    0.52
    l
    0.52
    ddy
    0.52
    stateParams
    0.52
     p
    0.51
    Activations Density 1.125%

    No Known Activations