© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228297
    Prev
    Next
    INDEX
    Explanations

    pursuing goals

    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_6_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
    in
    1.19
    ية
    1.06
    s
    0.98
    m
    0.95
    h
    0.93
    ే
    0.88
    ى
    0.86
    g
    0.85
    al
    0.81
    ين
    0.80
    POSITIVE LOGITS
    ति
    0.95
    й
    0.91
    /
    0.87
    ...
    0.83
    خی
    0.82
    :
    0.82
    ucking
    0.81
     αυτές
    0.81
    ]
    0.81
     estern
    0.80
    Activations Density 0.006%

    No Known Activations