© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60268
    Prev
    Next
    INDEX
    Explanations

    consider essential or filler

    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
    f
    0.97
     the
    0.90
    )
    0.87
    d
    0.85
    .
    0.84
     by
    0.83
     at
    0.82
     J
    0.79
     for
    0.79
     k
    0.76
    POSITIVE LOGITS
     مي‌
    0.84
     едно
    0.82
    ير
    0.79
     inactivació
    0.79
    ות
    0.78
     médicas
    0.75
     يعني
    0.74
     moléculas
    0.73
     evidencias
    0.73
    ﻓ
    0.73
    Activations Density 0.194%

    No Known Activations