© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161120
    Prev
    Next
    INDEX
    Explanations

    misspellings and grammar errors

    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_2_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
    ى
    1.30
    ahuje
    1.22
    на
    1.21
    ことができる
    1.21
    ко
    1.20
    ви
    1.20
    daki
    1.17
    cached
    1.17
    ાઓ
    1.16
    га
    1.15
    POSITIVE LOGITS
     $\
    1.39
    ។
    1.31
     to
    1.17
    '
    1.17
    。
    1.17
     n
    1.13
     r
    1.12
     p
    1.10
     f
    1.10
     u
    1.08
    Activations Density 0.000%

    No Known Activations