© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204123
    Prev
    Next
    INDEX
    Explanations

    actions or things

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    沘
    0.36
     mdl
    0.35
     Tokens
    0.35
    Tokens
    0.34
     edt
    0.33
    edt
    0.33
    शन
    0.33
    ក្រោម
    0.33
    Ûn
    0.32
    dern
    0.32
    POSITIVE LOGITS
     TO
    1.45
    TO
    1.44
     то
    1.39
     To
    1.29
     तो
    1.23
     장
    1.23
    To
    1.21
     تو
    1.11
    장
    1.10
    то
    0.96
    Activations Density 0.035%

    No Known Activations