© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110785
    Prev
    Next
    INDEX
    Explanations

    puberty

    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
    是
    1.41
    는
    1.31
    ations
    1.10
    ва
    1.08
    imes
    1.08
    с
    1.00
    íme
    0.99
    이어
    0.99
    )
    0.96
    و
    0.96
    POSITIVE LOGITS
    ש
    1.36
     wyk
    1.30
     kilka
    1.28
     yeni
    1.24
    t
    1.23
     drugi
    1.20
    א
    1.17
     powied
    1.16
     disponibile
    1.16
     potere
    1.15
    Activations Density 0.000%

    No Known Activations