© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88465
    Prev
    Next
    INDEX
    Explanations

    This is the core

    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
    ख्या
    0.36
    omag
    0.35
    鉱
    0.35
    CreateIndex
    0.35
    骧
    0.35
    isocyanate
    0.34
    চলে
    0.33
     comunque
    0.33
    コハマ
    0.32
     bling
    0.32
    POSITIVE LOGITS
     é
    0.36
     RS
    0.36
     coda
    0.35
     agen
    0.34
     kalian
    0.34
     guilds
    0.34
     पृष्ठ
    0.33
    ثال
    0.33
     Unt
    0.33
     字
    0.33
    Activations Density 0.025%

    No Known Activations