© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18440
    Prev
    Next
    INDEX
    Explanations

    section numbers followed by titles

    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_15_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
     orbits
    0.45
     aberrant
    0.44
     ის
    0.43
     monde
    0.43
     град
    0.42
    क्स
    0.42
    蕨
    0.41
    abilistic
    0.41
    র
    0.40
     ელ
    0.40
    POSITIVE LOGITS
    cemos
    0.43
     ઇચ્છ
    0.43
    chen
    0.42
    cary
    0.42
     Nauk
    0.41
     Commandments
    0.41
    ad
    0.41
    }$
    0.41
     Gyan
    0.41
    今日
    0.40
    Activations Density 0.001%

    No Known Activations