© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9601
    Prev
    Next
    INDEX
    Explanations

    code formatting

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    <0x0D>
    1.31
    </b>
    0.79
    </h2>
    0.76
    </a>
    0.73
    </i>
    0.72
    </code>
    0.67
    ‬
    0.60
    ↵↵
    0.60
     JL
    0.59
     $_{\
    0.58
    POSITIVE LOGITS
    岱
    0.77
     geometri
    0.74
     festgelegt
    0.74
     gehad
    0.74
    üs
    0.73
    <unused375>
    0.72
     propried
    0.71
     angepasst
    0.70
    cześ
    0.70
     zorgt
    0.69
    Activations Density 0.340%

    No Known Activations