© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218975
    Prev
    Next
    INDEX
    Explanations

    thickness

    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_47_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
     PUP
    0.43
    줍
    0.42
    ARAJ
    0.42
    𝑃
    0.40
    普
    0.38
     bete
    0.38
    фу
    0.37
    SORT
    0.37
    တ်
    0.37
    ARTI
    0.37
    POSITIVE LOGITS
    indrical
    0.48
    <0x8D>
    0.48
     thick
    0.47
     thickened
    0.46
    thickness
    0.43
     thicken
    0.43
    porters
    0.40
     ਦਿ
    0.40
     thickening
    0.40
    Thickness
    0.39
    Activations Density 0.001%

    No Known Activations