© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8053
    Prev
    Next
    INDEX
    Explanations

    full text of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    u
    3.29
    e
    2.67
    j
    2.64
    m
    2.63
    are
    2.43
    ো
    2.41
     начи
    2.40
    ores
    2.39
    rt
    2.39
    ed
    2.38
    POSITIVE LOGITS
    畊
    2.81
    )];
    2.40
    )])
    2.40
     audiovis
    2.25
     affrontare
    2.21
    зывать
    2.18
     soorten
    2.18
    Ре
    2.16
     conhe
    2.15
    contenedor
    2.13
    Activations Density 0.000%

    No Known Activations