© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50260
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     ď
    0.40
    ímp
    0.39
    vasena
    0.39
    irea
    0.39
    irii
    0.38
    serializing
    0.37
    cm
    0.36
    Auth
    0.36
     Collectively
    0.36
     listBox
    0.35
    POSITIVE LOGITS
    हे
    0.43
    hena
    0.40
    癖
    0.40
     сило
    0.38
    avoz
    0.37
     Sylvia
    0.37
    阿
    0.37
    Alo
    0.36
    ヘ
    0.36
    iene
    0.36
    Activations Density 0.005%

    No Known Activations