© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5075
    Prev
    Next
    INDEX
    Explanations

    small, common words

    oai_token-act-pair · gemini-2.0-flash

    Software and data processing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Anſ
    -0.87
     raiſ
    -0.85
     myſelf
    -0.84
     itſelf
    -0.84
     $_"
    -0.81
    ſelves
    -0.81
     doubtnut
    -0.81
     Jefus
    -0.80
     ſtand
    -0.78
     Efq
    -0.78
    POSITIVE LOGITS
    Com
    0.80
    lo
    0.80
    Su
    0.78
    Lo
    0.78
    Ar
    0.77
    Pa
    0.77
     Lo
    0.77
    Er
    0.76
    Ha
    0.76
    le
    0.76
    Activations Density 8.651%

    No Known Activations