© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 152163
    Prev
    Next
    INDEX
    Explanations

    groups of individuals

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     *}\
    0.39
    ፏ
    0.39
     coisas
    0.39
    arguments
    0.38
     *\
    0.38
    #}
    0.38
     _)
    0.37
     *}
    0.37
    弐
    0.36
    ্ি
    0.36
    POSITIVE LOGITS
     those
    0.58
     prone
    0.58
    <sup>
    0.55
     REPORT
    0.54
    -
    0.53
     تلك
    0.52
    prone
    0.50
     report
    0.50
     रिपोर्ट
    0.50
    those
    0.48
    Activations Density 0.003%

    No Known Activations