© 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. 161035
    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
     can
    1.23
    ri
    1.16
    de
    1.10
    ACH
    1.05
    si
    1.04
    s
    1.03
    can
    1.02
    ين
    1.01
    ار
    0.99
     to
    0.99
    POSITIVE LOGITS
    는
    1.18
    کز
    1.05
    高
    1.05
    ม่า
    1.04
    ກັບ
    1.02
    ılan
    1.01
    سک
    1.00
    یث
    1.00
    ح
    1.00
    ो
    0.99
    Activations Density 0.000%

    No Known Activations