© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199360
    Prev
    Next
    INDEX
    Explanations

    **pen** **tip** sizes **0.5mm**, **0.7mm**, **medium**

    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_12_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
    reactant
    0.52
    ্বে
    0.51
     डैम
    0.49
    corpus
    0.48
    <0xB4>
    0.47
    ).(
    0.47
    agad
    0.47
     subchapter
    0.46
     પ્રતિ
    0.46
    sofar
    0.46
    POSITIVE LOGITS
    ﻳ
    0.54
    "
    0.53
    São
    0.52
    Others
    0.51
    Sz
    0.48
     że
    0.48
    ùng
    0.47
    Jeg
    0.47
     multiplex
    0.47
    Université
    0.47
    Activations Density 0.001%

    No Known Activations