© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39896
    Prev
    Next
    INDEX
    Explanations

    base64 encoding

    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_57_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
    э
    0.52
    ж
    0.49
     э
    0.48
     k
    0.47
    же
    0.46
    къ
    0.46
    k
    0.46
    б
    0.45
    К
    0.44
     h
    0.42
    POSITIVE LOGITS
    氚
    0.46
     αυ
    0.42
     Τα
    0.39
     nonatomic
    0.39
     stochastic
    0.38
     uncertainty
    0.38
    肱
    0.38
     પા
    0.38
     DNR
    0.38
     ε
    0.38
    Activations Density 0.000%

    No Known Activations