© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84224
    Prev
    Next
    INDEX
    Explanations

    data over years

    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_23_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
     نست
    0.45
    嘴角
    0.41
    ી
    0.39
     much
    0.39
    ියා
    0.38
     নুরুল
    0.36
     ముందుకు
    0.36
    ద్దు
    0.36
     আসবে
    0.35
     العن
    0.35
    POSITIVE LOGITS
     spoloč
    0.42
    уна
    0.42
     emitted
    0.39
    released
    0.39
    Ꮓ
    0.39
     Morrow
    0.39
    𒌷
    0.39
    STONE
    0.39
     積
    0.39
     मातृ
    0.39
    Activations Density 0.001%

    No Known Activations