© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139026
    Prev
    Next
    INDEX
    Explanations

    get to, get started, get back

    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_37_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
    caria
    0.40
     into
    0.37
     연락
    0.37
    鋆
    0.36
     rem
    0.35
     সদস্যদের
    0.35
    つい
    0.35
     Gutierrez
    0.35
    回應
    0.34
    ^{(\
    0.34
    POSITIVE LOGITS
    fuzzy
    0.40
     Fuzzy
    0.39
     meditate
    0.39
     փ
    0.38
     നട
    0.38
     towns
    0.37
    WithSize
    0.36
     asked
    0.36
     Blackstone
    0.36
     नए
    0.36
    Activations Density 0.003%

    No Known Activations