© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42659
    Prev
    Next
    INDEX
    Explanations

    natural history, arts, science

    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_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
     on
    0.71
    ا
    0.64
    mAb
    0.60
    transmitter
    0.58
    toon
    0.57
    其他
    0.56
    f
    0.55
    tox
    0.55
    াইয়৷
    0.55
     in
    0.54
    POSITIVE LOGITS
    ות
    0.72
    ’
    0.68
     esigenze
    0.67
     specifiche
    0.66
    ﺓ
    0.66
    হ
    0.64
    ът
    0.64
     MODEL
    0.64
     pozitiv
    0.63
     I
    0.63
    Activations Density 0.000%

    No Known Activations