© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17886
    Prev
    Next
    INDEX
    Explanations

    asteroid meteorite

    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_34_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
     nasa
    0.44
    ቷ
    0.43
    地球
    0.40
     NASA
    0.39
     distance
    0.39
     planet
    0.38
     pickup
    0.38
    距离
    0.38
    Venus
    0.38
    dangerous
    0.38
    POSITIVE LOGITS
     柄
    0.44
    кость
    0.43
    GPA
    0.42
    iegler
    0.38
     AFRICA
    0.37
    柄
    0.37
    ств
    0.36
    ించి
    0.36
     int
    0.36
    jhelp
    0.36
    Activations Density 0.010%

    No Known Activations