© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212218
    Prev
    Next
    INDEX
    Explanations

    modelmodel numbers and abbreviations

    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_5_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
    \
    1.52
    ”,
    1.09
     I
    1.07
    AKE
    1.05
     பேர்
    1.05
     tortillas
    1.02
    É
    1.02
    습니다
    1.01
    Ι
    1.01
    ní
    0.96
    POSITIVE LOGITS
    un
    1.47
    in
    1.45
    a
    1.42
    j
    1.37
    9
    1.35
    ر
    1.32
    ка
    1.28
    to
    1.24
    д
    1.23
    and
    1.22
    Activations Density 0.000%

    No Known Activations