© 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-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161967
    Prev
    Next
    INDEX
    Explanations

    lately, soundly, quickly

    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
    .
    1.30
    '
    1.27
    )
    1.24
    )(
    0.92
     tangy
    0.92
    )،
    0.91
     m
    0.91
     b
    0.89
     e
    0.89
     estrogen
    0.88
    POSITIVE LOGITS
    and
    2.08
    ing
    1.40
    d
    1.39
    та
    1.38
    ,
    1.34
    ни
    1.23
    ના
    1.21
    g
    1.20
    ud
    1.16
    t
    1.16
    Activations Density 0.001%

    No Known Activations