© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230713
    Prev
    Next
    INDEX
    Explanations

    specific versions

    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_6_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
    cimentos
    0.84
    패
    0.77
    ER
    0.76
     sociological
    0.74
    voir
    0.73
    夋
    0.73
     turbulent
    0.72
    ל
    0.72
     be
    0.71
    ፈላጊ
    0.71
    POSITIVE LOGITS
    t
    1.41
    ’
    1.13
    ta
    1.01
    -
    1.00
    '
    0.89
    tt
    0.82
    ")}
    0.80
    "},
    0.80
    tik
    0.80
    r
    0.80
    Activations Density 0.006%

    No Known Activations