© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80974
    Prev
    Next
    INDEX
    Explanations

    that

    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_53_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
     jotka
    0.33
     különböző
    0.32
     respectivas
    0.32
    粝
    0.31
    㞰
    0.31
     جميلة
    0.31
    饒
    0.31
    CAO
    0.31
    impanan
    0.31
     محصولات
    0.31
    POSITIVE LOGITS
    ানু
    0.35
     হুঁ
    0.32
     ((
    0.31
     äh
    0.31
     conclud
    0.31
    …
    0.31
     concurrency
    0.31
     heave
    0.31
     haven
    0.30
     they
    0.30
    Activations Density 0.010%

    No Known Activations