© 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. 53875
    Prev
    Next
    INDEX
    Explanations

    code actions

    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
     wê
    0.39
     Chees
    0.37
    꺼
    0.37
    稣
    0.37
     sfai
    0.37
     Benjamin
    0.37
    FocusValue
    0.37
    系列的
    0.37
    ljivo
    0.36
    ەڵ
    0.36
    POSITIVE LOGITS
     "/
    0.49
    After
    0.48
    Function
    0.44
    SignUp
    0.43
     waitFor
    0.42
     signUp
    0.42
     increase
    0.41
     "",
    0.41
    signIn
    0.41
    signUp
    0.41
    Activations Density 0.002%

    No Known Activations