© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14490
    Prev
    Next
    INDEX
    Explanations

    ICE, Convers, MP, Pap, Other

    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_15_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
    eleration
    0.17
    icots
    0.16
    }$,
    0.15
    Ich
    0.15
    aties
    0.15
     Hohen
    0.15
    atost
    0.15
    },
    0.15
     Eo
    0.15
    from
    0.15
    POSITIVE LOGITS
     déplacer
    0.18
     문제는
    0.16
     ประเทศ
    0.16
    市场上
    0.16
     reinstall
    0.16
    -
    0.15
     reuse
    0.15
     문제를
    0.15
    मीर
    0.15
    鸪
    0.15
    Activations Density 0.017%

    No Known Activations