© 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-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51216
    Prev
    Next
    INDEX
    Explanations

    influence or trends

    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_55_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
    upon
    0.40
     ramus
    0.40
     оки
    0.39
    signOut
    0.38
    fromUtf
    0.37
    stroke
    0.36
    াজি
    0.36
    }$(
    0.36
    別に
    0.35
     spades
    0.35
    POSITIVE LOGITS
     promoted
    0.62
     advocated
    0.54
     induced
    0.49
     prevailing
    0.48
     tend
    0.46
     initiated
    0.46
     affected
    0.46
     cognition
    0.46
     boosted
    0.45
     stimulated
    0.45
    Activations Density 0.001%

    No Known Activations