© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49939
    Prev
    Next
    INDEX
    Explanations

    }

    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_55_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
     '../../../
    0.38
    หมู่
    0.37
    steering
    0.36
     quen
    0.35
    𒀀
    0.34
    dicke
    0.34
    ৬৮
    0.33
    都被
    0.33
    已经被
    0.33
     '../../
    0.33
    POSITIVE LOGITS
     collapsing
    0.45
     crashing
    0.44
     difficult
    0.43
     milliseconds
    0.43
     overw
    0.43
    Difficult
    0.43
     collapse
    0.42
     behaviors
    0.41
     overwrite
    0.41
     biofilms
    0.41
    Activations Density 0.002%

    No Known Activations