© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58280
    Prev
    Next
    INDEX
    Explanations

    severing ties

    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_2_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
    w
    1.01
    ktiv
    0.96
    SB
    0.92
    hatikan
    0.89
    pt
    0.88
    These
    0.88
    tragung
    0.86
    y
    0.86
    gn
    0.85
    Semitism
    0.85
    POSITIVE LOGITS
     of
    1.85
    ↵
    1.45
     you
    1.27
    }
    1.25
     ۳
    1.20
    ก
    1.19
     ৩
    1.16
     של
    1.15
    ação
    1.12
     Poco
    1.11
    Activations Density 0.000%

    No Known Activations