© 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. 113045
    Prev
    Next
    INDEX
    Explanations

    ethnologue, ethnography, ethnicity

    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
    é
    1.50
    <0x0D>
    1.44
    ం
    1.40
    ี
    1.30
    m
    1.27
    م
    1.26
    it
    1.25
    aj
    1.25
    p
    1.24
    ak
    1.22
    POSITIVE LOGITS
    .
    1.22
    dad
    1.06
    ]_
    0.99
     좋습니다
    0.99
    |.
    0.98
    galkan
    0.96
    産の
    0.96
     ی
    0.95
    slidesPerGroup
    0.95
    ].
    0.93
    Activations Density 0.000%

    No Known Activations