© 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. 134753
    Prev
    Next
    INDEX
    Explanations

    expertise, locator, hook

    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
    ’,
    0.86
     می‌کند
    0.84
    ٠
    0.83
    ,’
    0.83
    ί
    0.82
    ]
    0.80
    ،
    0.77
     probationary
    0.77
    </th>
    0.75
    軐
    0.75
    POSITIVE LOGITS
    on
    1.40
    m
    1.26
    '
    1.21
    h
    1.06
    w
    1.06
    ING
    1.05
    מ
    1.04
    ات
    1.03
    is
    1.02
    ك
    1.02
    Activations Density 0.000%

    No Known Activations