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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261301
    Prev
    Next
    INDEX
    Explanations

    Rumiho Akiha

    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_5_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
    </strong>
    1.28
    </h2>
    1.26
    </h3>
    1.23
    to
    1.20
    </h1>
    1.13
    </h4>
    1.13
    </b>
    1.13
    <0x0D>
    1.06
    </u>
    1.05
    </span>
    1.03
    POSITIVE LOGITS
    л
    1.59
    س
    1.49
    ح
    1.47
    on
    1.45
    es
    1.45
    ens
    1.42
    ב
    1.33
    ъ
    1.26
    ز
    1.25
    ח
    1.23
    Activations Density 0.000%

    No Known Activations