© 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. 162126
    Prev
    Next
    INDEX
    Explanations

    per capita metric

    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
    \
    1.08
    습니다
    1.03
     as
    0.95
    }$
    0.94
    
    0.94
    have
    0.93
    c
    0.92
     sizlerle
    0.89
    ००
    0.88
    se
    0.87
    POSITIVE LOGITS
    ை
    1.41
    ת
    1.41
    는
    1.30
     in
    1.25
    い
    1.23
    ב
    1.15
    ة
    1.13
    も
    1.05
     not
    1.03
    า
    1.02
    Activations Density 0.000%

    No Known Activations