© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156969
    Prev
    Next
    INDEX
    Explanations

    phal/phant arch/arches

    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_2_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
    </h2>
    1.30
     on
    1.18
    لی
    1.17
    ί
    1.09
    ור
    1.09
    ０
    1.09
    হ
    1.08
     uzys
    1.05
    ре
    1.04
     তুমি
    1.04
    POSITIVE LOGITS
    ne
    1.15
    ed
    1.02
    ópolis
    1.02
    ().
    1.00
    (
    0.96
     d
    0.95
    at
    0.92
    ocellular
    0.92
    ٨
    0.92
    ٣
    0.91
    Activations Density 0.000%

    No Known Activations