© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23555
    Prev
    Next
    INDEX
    Explanations

    boy Min Hor

    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_56_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
     refreshed
    0.40
    走路
    0.38
    umping
    0.38
    eme
    0.37
    Centered
    0.35
    ствует
    0.35
    iedade
    0.35
    徙
    0.34
    IH
    0.34
    remen
    0.34
    POSITIVE LOGITS
    ce
    0.42
    hora
    0.39
    ष्‍
    0.36
    ice
    0.36
     instrumentos
    0.36
     posti
    0.36
     cef
    0.35
    äns
    0.35
    하
    0.35
    це
    0.35
    Activations Density 0.021%

    No Known Activations