© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13384
    Prev
    Next
    INDEX
    Explanations

    more thanas

    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_15_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    unting
    0.19
    撐
    0.19
     Brits
    0.18
    án
    0.18
     Methodology
    0.18
    يين
    0.18
     XM
    0.18
    iunea
    0.18
     no
    0.18
     vyp
    0.18
    POSITIVE LOGITS
    Backward
    0.20
    向け
    0.18
    Cipher
    0.17
    ]^{+}$
    0.17
     miner
    0.17
     Alkali
    0.17
    }+\
    0.17
    }+
    0.17
    Brows
    0.17
    Call
    0.16
    Activations Density 0.075%

    No Known Activations