© 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
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 91026
    Prev
    Next
    INDEX
    Explanations

    Open followed by Lord, Therm, Search, Question, or Nature

    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_3_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
    nél
    0.69
    ва
    0.64
    uğ
    0.63
    hx
    0.62
    л
    0.62
    nagar
    0.61
    nox
    0.61
    nY
    0.58
    hj
    0.56
    nX
    0.56
    POSITIVE LOGITS
    1
    0.90
     i
    0.77
    es
    0.74
    2
    0.74
    ের
    0.71
    ی
    0.69
     demur
    0.68
    s
    0.68
    i
    0.64
    ه
    0.64
    Activations Density 0.006%

    No Known Activations