© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261828
    Prev
    Next
    INDEX
    Explanations

    year old carpenter

    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_22_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
     hubs
    0.49
     जो
    0.45
     생
    0.44
     ऑफ़
    0.43
     اطراف
    0.43
    ecode
    0.42
     reward
    0.42
    েক
    0.42
    ཕ
    0.42
    রাশ
    0.41
    POSITIVE LOGITS
    amente
    0.52
    衔
    0.52
    )*
    0.47
    精致
    0.46
     Dever
    0.46
    .*
    0.45
    ))(
    0.45
    ]))
    0.44
    *,
    0.44
     detto
    0.44
    Activations Density 0.000%

    No Known Activations