© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144964
    Prev
    Next
    INDEX
    Explanations

    commuter train and rail

    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_0_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
    B
    1.54
     malicious
    1.52
    AZ
    1.41
     or
    1.33
     orchestral
    1.33
    า
    1.33
    N
    1.32
    ক
    1.31
    и
    1.28
    यों
    1.27
    POSITIVE LOGITS
    3
    1.82
    st
    1.55
    la
    1.44
    gação
    1.38
    4
    1.37
    ra
    1.31
    pre
    1.29
    ret
    1.29
    5
    1.27
    ión
    1.27
    Activations Density 0.000%

    No Known Activations