© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167155
    Prev
    Next
    INDEX
    Explanations

    `password`, `hashed`, `encriptada`, `encriptar`, `sha256`, `hashlib`, `PASSWORD_DEFAULT`, `plain text`

    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_31_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
    螞
    0.52
     পিঁপ
    0.45
     ants
    0.45
     formic
    0.44
     الرحيم
    0.43
     erit
    0.42
    ImageView
    0.42
     পিঁপড়া
    0.42
     numeros
    0.41
    🐜
    0.41
    POSITIVE LOGITS
    ేశారు
    0.38
    なくな
    0.38
    Ų
    0.38
    лото
    0.37
     flue
    0.36
     Elektrokhimiya
    0.36
    ági
    0.36
    ياء
    0.36
    azaki
    0.35
    работ
    0.35
    Activations Density 0.028%

    No Known Activations