© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161369
    Prev
    Next
    INDEX
    Explanations

    prefix "os" then common words

    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_2_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
    2
    1.65
    و
    1.48
    ุ
    1.45
    9
    1.44
    6
    1.43
    1
    1.33
    3
    1.30
    4
    1.28
    اب
    1.19
    that
    1.16
    POSITIVE LOGITS
    '
    1.40
    ມັນ
    1.27
     be
    1.27
     pérdidas
    1.07
    ０
    1.06
    íř
    0.99
    اں
    0.98
     Been
    0.98
     prácticas
    0.97
    க்கு
    0.96
    Activations Density 0.000%

    No Known Activations