© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25950
    Prev
    Next
    INDEX
    Explanations

    atomic types and structures

    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_10_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
    j
    0.71
    v
    0.70
    ä
    0.64
     Cras
    0.58
    h
    0.56
     Schuld
    0.56
    <0x0D>
    0.54
     hObject
    0.54
    os
    0.53
     Sprach
    0.53
    POSITIVE LOGITS
     나가
    0.64
     exacerbated
    0.56
    ￠
    0.55
     njega
    0.55
     אז
    0.55
    वंत
    0.54
     पार्षद
    0.54
    isiä
    0.54
    <unused2141>
    0.54
    spent
    0.53
    Activations Density 0.000%

    No Known Activations