© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147216
    Prev
    Next
    INDEX
    Explanations

    own

    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_59_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
     direct
    0.44
     Direct
    0.41
     کولو
    0.39
    iyy
    0.39
     직
    0.38
    Direct
    0.38
     अगली
    0.37
     చో
    0.37
    㓩
    0.37
    direct
    0.37
    POSITIVE LOGITS
     own
    0.81
     eigene
    0.67
    Own
    0.67
    own
    0.66
     propres
    0.62
     Own
    0.61
     собственных
    0.61
     eigenen
    0.59
     vlastní
    0.59
     włas
    0.57
    Activations Density 0.002%

    No Known Activations