© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130150
    Prev
    Next
    INDEX
    Explanations

    beginning of CONVERSATION

    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_6_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
    the
    1.08
    ro
    0.86
    ض
    0.86
    тор
    0.82
    어졌
    0.81
    的分
    0.81
    zeitig
    0.80
    ρι
    0.79
    to
    0.78
    ru
    0.78
    POSITIVE LOGITS
    \
    1.20
    ing
    1.20
    '
    1.14
    us
    1.08
    ار
    1.08
    $,
    1.05
    al
    1.02
    িং
    1.02
    ]:
    1.00
    อยาก
    0.98
    Activations Density 0.000%

    No Known Activations