© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41760
    Prev
    Next
    INDEX
    Explanations

    password verification function calls

    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_22_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
    둠
    0.40
    씀
    0.39
     都市
    0.39
     unconditional
    0.39
     ಹೃ
    0.38
    亓
    0.38
    osť
    0.38
    ()'
    0.38
    See
    0.37
     život
    0.37
    POSITIVE LOGITS
     बंग
    0.40
    directives
    0.38
    虜
    0.38
     Atelier
    0.38
     directives
    0.37
    unet
    0.36
    cciones
    0.36
    最高
    0.35
    ügen
    0.35
     طريقة
    0.35
    Activations Density 0.000%

    No Known Activations