© 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. 4141
    Prev
    Next
    INDEX
    Explanations

    the word "bit" and words related to measure or degree

    oai_token-act-pair · gemini-2.0-flash

    subjective commentary

    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
    tvguidetime
    -0.98
     pleaſure
    -0.84
     Majefty
    -0.82
    findpost
    -0.81
    [:,:,
    -0.79
    .)}
    -0.77
     Jefus
    -0.76
    !")
    -0.74
     Houſe
    -0.73
    }}$\\
    -0.73
    POSITIVE LOGITS
     much
    0.69
    much
    0.53
     poco
    0.52
     in
    0.51
    Much
    0.50
    Enough
    0.50
     many
    0.49
     to
    0.49
     bete
    0.49
    дів
    0.48
    Activations Density 1.339%

    No Known Activations