© 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. 112264
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    i
    1.40
    지
    1.21
    The
    1.20
    ي
    1.19
    a
    1.09
    7
    1.09
    the
    1.08
    dı
    1.07
    য়ের
    1.03
    ٹ
    1.03
    POSITIVE LOGITS
     be
    1.15
     it
    1.06
    ige
    0.96
    olla
    0.96
    ن
    0.95
    ಿದ
    0.94
    िया
    0.94
    ICK
    0.94
    ある
    0.91
    ime
    0.91
    Activations Density 0.000%

    No Known Activations