© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80544
    Prev
    Next
    INDEX
    Explanations

    Pinecone, pineapple, script, needles

    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_0_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
    '
    1.88
    </h3>
    1.71
    ة
    1.60
    </h1>
    1.58
    </h5>
    1.49
    ‬
    1.41
    </blockquote>
    1.38
    ing
    1.38
    és
    1.32
    </b>
    1.30
    POSITIVE LOGITS
    inę
    2.05
    in
    1.84
    inį
    1.80
    ל
    1.55
    ０
    1.55
    на
    1.38
    ти
    1.38
     ۸
    1.35
    র
    1.35
    ס
    1.32
    Activations Density 0.001%

    No Known Activations