© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 121009
    Prev
    Next
    INDEX
    Explanations

    Creepypasta, anime, Japanese words

    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_38_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
    春夏
    0.41
     মাহ
    0.38
    कद
    0.38
    食堂
    0.38
     acorde
    0.35
     வாழ்
    0.35
    ຟ
    0.35
     Madras
    0.35
     nurturing
    0.35
     यशवंत
    0.34
    POSITIVE LOGITS
     Lords
    0.46
     Lord
    0.42
     Kik
    0.41
    Lord
    0.41
     LORD
    0.40
    LORD
    0.40
     Mecklenburg
    0.40
    缚
    0.40
     ఉత్త
    0.39
     Kag
    0.39
    Activations Density 0.004%

    No Known Activations