© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124088
    Prev
    Next
    INDEX
    Explanations

    LLaMA-13B

    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_3_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
    ש
    0.75
    ین
    0.70
    ہ
    0.69
    ल
    0.68
    يل
    0.68
     kerajaan
    0.68
    ле
    0.67
    ینگ
    0.67
    м
    0.67
    ش
    0.65
    POSITIVE LOGITS
    a
    1.29
    was
    0.81
    at
    0.79
     was
    0.79
    were
    0.72
    in
    0.69
    have
    0.66
    ađ
    0.66
    you
    0.65
    am
    0.64
    Activations Density 0.001%

    No Known Activations