© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50223
    Prev
    Next
    INDEX
    Explanations

    did

    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
    holy
    0.38
    getPage
    0.38
    द्योग
    0.36
    roleum
    0.35
    ckså
    0.34
    ន្តែ
    0.34
    ngrx
    0.33
    盜
    0.33
    šću
    0.33
    getInt
    0.33
    POSITIVE LOGITS
     did
    1.92
    did
    1.89
    Did
    1.85
     Did
    1.81
     uz
    1.67
    DID
    1.48
     DID
    1.41
     Uz
    1.34
    Uz
    1.31
     уз
    1.27
    Activations Density 0.005%

    No Known Activations