© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 182376
    Prev
    Next
    INDEX
    Explanations

    package manager instructions

    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_29_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
    }^\
    0.42
    .|__
    0.42
    表的
    0.40
    Პ
    0.39
     Kxa
    0.39
    .]:
    0.37
    𒀊
    0.37
    ⊟
    0.37
    뀔
    0.36
     marchand
    0.36
    POSITIVE LOGITS
     organization
    0.42
    ly
    0.42
    ac
    0.39
     (
    0.38
    sleep
    0.38
     people
    0.38
    lap
    0.38
    cl
    0.37
     replace
    0.37
     takes
    0.37
    Activations Density 0.004%

    No Known Activations