© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208306
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     अका
    0.44
     առաջ
    0.43
     जेव्हा
    0.42
    estructura
    0.42
    вена
    0.42
     क
    0.41
     لان
    0.41
     जब
    0.40
    ancourt
    0.40
    崞
    0.40
    POSITIVE LOGITS
     Speakers
    0.36
     Teilnehmer
    0.35
     speaker
    0.34
     voters
    0.34
     Correspondent
    0.34
     speakers
    0.33
     Supporters
    0.33
    کنندگان
    0.33
    PutMapping
    0.33
     Filmm
    0.32
    Activations Density 0.000%

    No Known Activations