© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13839
    Prev
    Next
    INDEX
    Explanations

    x and y axis

    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_40_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
    subsection
    0.42
    hyperref
    0.41
    angel
    0.38
     വല
    0.37
    三分
    0.36
     angelic
    0.36
    笘
    0.35
    jaman
    0.35
     Assoc
    0.34
     группы
    0.34
    POSITIVE LOGITS
     axis
    1.49
    Axis
    1.34
     Axis
    1.34
    axis
    1.30
    軸
    1.26
     axes
    1.25
    轴
    1.23
     eixo
    1.05
    axes
    1.04
     محور
    1.01
    Activations Density 0.077%

    No Known Activations