© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36278
    Prev
    Next
    INDEX
    Explanations

    thought about

    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_11_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
    럭
    0.58
     affirmations
    0.57
    ﻒ
    0.57
     یا
    0.55
    StackTrace
    0.54
    férence
    0.54
    鶘
    0.54
    皇后
    0.53
    总理
    0.53
    𝗚
    0.53
    POSITIVE LOGITS
    с
    0.69
    س
    0.68
    z
    0.65
     BEEN
    0.60
    ن
    0.59
    s
    0.59
     been
    0.59
    v
    0.57
    n
    0.55
     číslo
    0.54
    Activations Density 0.003%

    No Known Activations