© 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. 23706
    Prev
    Next
    INDEX
    Explanations

    also/too

    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
     Yo
    1.23
    Yo
    1.23
    Self
    1.20
    自
    1.20
     요
    1.19
     yo
    1.17
     Self
    1.13
     self
    1.09
    요
    1.09
     tự
    1.06
    POSITIVE LOGITS
    도
    0.54
     भी
    0.46
     Đ
    0.46
     também
    0.45
     også
    0.42
     тоже
    0.42
    ও
    0.41
     también
    0.40
     také
    0.38
     thanked
    0.38
    Activations Density 0.003%

    No Known Activations