© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140004
    Prev
    Next
    INDEX
    Explanations

    shaping materials

    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_46_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
    㹂
    0.44
    之中
    0.38
    ᆫ
    0.38
     Learners
    0.37
     DAP
    0.37
    敀
    0.36
    ɑ
    0.36
    郏
    0.36
     पोर्न
    0.36
    𝙫
    0.35
    POSITIVE LOGITS
     carved
    0.80
     woven
    0.80
     sculpted
    0.72
     sculpt
    0.72
    layered
    0.71
     layered
    0.70
     weave
    0.70
     inject
    0.69
     molded
    0.69
     threaded
    0.68
    Activations Density 0.297%

    No Known Activations