© 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. 109381
    Prev
    Next
    INDEX
    Explanations

    starts of words in different languages

    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
    {
    1.02
    },
    0.84
    (
    0.69
    :
    0.69
     as
    0.64
    }
    0.63
    $
    0.61
    0
    0.60
    =
    0.59
    ],
    0.58
    POSITIVE LOGITS
    will
    0.75
    ى
    0.73
    has
    0.69
    тың
    0.68
    లో
    0.66
    so
    0.63
    та
    0.63
    thing
    0.62
    ıştır
    0.61
    ne
    0.60
    Activations Density 0.000%

    No Known Activations