© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253884
    Prev
    Next
    INDEX
    Explanations

    Enumer

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    らい
    0.39
    IZING
    0.38
    য়ান
    0.37
    वेस्ट
    0.37
    佇
    0.36
    ţi
    0.36
    ロジー
    0.36
    ರುತ್ತ
    0.35
     घाट
    0.35
     가지
    0.35
    POSITIVE LOGITS
     Able
    0.47
    ability
    0.46
    능
    0.43
     able
    0.41
    ABLE
    0.40
    abilità
    0.40
    ible
    0.39
    Able
    0.39
     schop
    0.38
     Stellung
    0.37
    Activations Density 0.001%

    No Known Activations