© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32324
    Prev
    Next
    INDEX
    Explanations

    away

    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_50_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
    설
    0.41
    전을
    0.37
    akter
    0.37
    =(-
    0.37
    älte
    0.36
    ISES
    0.36
    抬头
    0.36
    设
    0.36
    má
    0.36
    统一
    0.35
    POSITIVE LOGITS
     away
    2.44
     Away
    2.19
    Away
    2.08
    away
    1.98
     AWAY
    1.88
    aways
    1.10
     weg
    0.96
     bort
    0.92
    掉
    0.91
    远离
    0.89
    Activations Density 0.099%

    No Known Activations