© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79536
    Prev
    Next
    INDEX
    Explanations

    need from you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assistance
    0.36
    representing
    0.36
    援助
    0.36
    <h6>
    0.35
    dtype
    0.35
    descricao
    0.34
    までも
    0.34
    perluan
    0.34
     formally
    0.34
     सहायता
    0.34
    POSITIVE LOGITS
     ustedes
    0.38
     Tarr
    0.38
     JO
    0.37
     Tomb
    0.37
     ஒதுக்க
    0.37
    듬
    0.36
    덟
    0.36
    が増
    0.36
     landmark
    0.36
     physicists
    0.35
    Activations Density 0.007%

    No Known Activations