© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157205
    Prev
    Next
    INDEX
    Explanations

    Sisyphus, quinsy, mississippi

    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_2_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
    are
    1.66
    AR
    1.66
    a
    1.55
    on
    1.48
    _
    1.38
    of
    1.32
    were
    1.31
    ur
    1.30
    AL
    1.25
    ।
    1.25
    POSITIVE LOGITS
    تين
    1.24
    י
    1.16
    ться
    1.09
    तः
    1.09
    دن
    1.09
    ůže
    1.08
    сную
    1.07
    ство
    1.06
    ש
    1.05
    తో
    1.04
    Activations Density 0.001%

    No Known Activations