© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237058
    Prev
    Next
    INDEX
    Explanations

    passenger

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Participant
    0.53
     participant
    0.49
     Participants
    0.46
     Patient
    0.46
     Pure
    0.46
     pure
    0.46
    Pure
    0.44
    잉
    0.44
    Ways
    0.44
     пациента
    0.43
    POSITIVE LOGITS
    uild
    0.43
    +](=
    0.40
     śmierci
    0.38
     halted
    0.38
    }"]
    0.38
    stopping
    0.37
    ]')
    0.37
     postpon
    0.36
    ี่ยง
    0.36
    executions
    0.36
    Activations Density 0.001%

    No Known Activations