© 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. 134576
    Prev
    Next
    INDEX
    Explanations

    related to

    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
    is
    1.31
    in
    1.27
    ad
    1.05
    ن
    1.02
     was
    1.01
    ’
    1.01
    ong
    0.97
    c
    0.96
    a
    0.94
    ian
    0.93
    POSITIVE LOGITS
     obstáculos
    1.05
     rozpoczę
    0.98
    వంటి
    0.97
     desarroll
    0.96
     Itália
    0.95
     другими
    0.93
     tú
    0.91
     poderá
    0.91
     ayudará
    0.91
    🇶
    0.90
    Activations Density 0.002%

    No Known Activations