© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196350
    Prev
    Next
    INDEX
    Explanations

    Ibid

    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_46_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
    toISO
    0.38
    ुसार
    0.36
    addComponent
    0.35
    악
    0.35
    issy
    0.34
     stirs
    0.34
    Enemy
    0.34
    므로
    0.34
    ~!
    0.34
    金を
    0.33
    POSITIVE LOGITS
     ib
    1.65
     Ibid
    1.56
     Ib
    1.53
     ibid
    1.50
    Ibid
    1.40
    Ib
    1.36
    ibid
    1.27
     id
    1.22
     Id
    1.21
    ib
    1.18
    Activations Density 0.001%

    No Known Activations