© 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. 240609
    Prev
    Next
    INDEX
    Explanations

    legal / formal roles

    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
     оча
    0.44
    ars
    0.37
    ѝ
    0.37
     Yoshida
    0.36
     ώστε
    0.36
     Ried
    0.36
     Enlarg
    0.36
     `--
    0.35
    cid
    0.35
     შეს
    0.35
    POSITIVE LOGITS
    Seeking
    0.38
    ുവരി
    0.36
     तीनों
    0.36
     dit
    0.35
    GRANTED
    0.34
     ఒ
    0.34
     décidé
    0.34
     мате
    0.34
     compro
    0.34
    claw
    0.34
    Activations Density 0.001%

    No Known Activations