© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11500
    Prev
    Next
    INDEX
    Explanations

    references to online education, streaming, and video recording using specific software

    oai_token-act-pair · gemini-2.0-flash

    recording

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Artik
    -0.64
    endsection
    -0.50
     consultato
    -0.47
     dra
    -0.47
     lat
    -0.46
     Artik
    -0.46
     Witkin
    -0.46
    .~(\
    -0.45
     vedi
    -0.44
    KOV
    -0.44
    POSITIVE LOGITS
     recorded
    2.48
     recording
    2.45
     Recorded
    2.17
    recorded
    2.17
     Recording
    2.16
    recording
    2.09
    Recorded
    2.08
    Recording
    2.06
     recordings
    2.03
     RECORD
    2.03
    Activations Density 4.353%

    No Known Activations