© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195202
    Prev
    Next
    INDEX
    Explanations

    creation patterns

    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_4_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
    .
    0.16
    ⅔
    0.15
     servizio
    0.15
     renom
    0.14
     bloke
    0.14
     ת
    0.14
     jail
    0.14
     raid
    0.14
    㶲
    0.14
     presidente
    0.14
    POSITIVE LOGITS
    क
    0.21
    is
    0.20
    r
    0.20
    ק
    0.20
    a
    0.19
    자
    0.19
    א
    0.18
    l
    0.18
    </td>
    0.17
    ق
    0.17
    Activations Density 0.004%

    No Known Activations