© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108769
    Prev
    Next
    INDEX
    Explanations

    please be advised

    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_2_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
    ek
    1.17
    em
    1.16
    وم
    1.13
    ali
    1.11
    er
    1.03
    ون
    0.97
    ed
    0.96
    ä
    0.96
    ل
    0.95
    し
    0.95
    POSITIVE LOGITS
    :
    1.54
    ,
    1.38
    ,}
    1.20
     axles
    1.16
    _
    1.13
    }$,
    1.12
     основу
    1.12
    }$.
    1.11
    }=
    1.06
    )$,
    1.06
    Activations Density 0.000%

    No Known Activations