© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61661
    Prev
    Next
    INDEX
    Explanations

    contain or containment

    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_11_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
    '
    0.80
    ’
    0.75
    description
    0.59
    IM
    0.59
     Unternehmen
    0.57
    Contents
    0.56
     RH
    0.55
     anthem
    0.55
    M
    0.55
    虽
    0.55
    POSITIVE LOGITS
     supersymmetric
    0.76
     satta
    0.64
    kách
    0.61
     психи
    0.60
    ørte
    0.60
     invariant
    0.59
    şağı
    0.59
     sadistic
    0.57
     invariance
    0.57
    uldig
    0.57
    Activations Density 0.002%

    No Known Activations