© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240717
    Prev
    Next
    INDEX
    Explanations

    code structural elements

    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_25_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
     तुझ्या
    0.42
    codiles
    0.40
    ೇಷ
    0.40
     cunning
    0.39
    硖
    0.37
    rq
    0.36
    ijas
    0.36
    urenc
    0.36
     കഴ
    0.36
     wirken
    0.36
    POSITIVE LOGITS
     amet
    0.44
    À
    0.42
    minimize
    0.40
     ने
    0.39
    皆様
    0.39
    deposition
    0.38
    𝚊
    0.38
    ат
    0.38
    您
    0.38
    ের
    0.38
    Activations Density 0.001%

    No Known Activations