© 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. 230779
    Prev
    Next
    INDEX
    Explanations

    parler, habla, speak

    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
    in
    1.30
    ).
    1.17
    с
    1.14
    }.
    1.13
    го
    1.12
    ot
    1.07
    та
    1.06
    كم
    1.05
    𝐭
    1.05
    ة
    1.03
    POSITIVE LOGITS
    '
    1.59
    ’
    1.00
     revê
    0.91
     ouvre
    0.91
     параметры
    0.91
     środków
    0.90
     значение
    0.89
     lysates
    0.89
     acredit
    0.88
    É
    0.85
    Activations Density 0.000%

    No Known Activations