© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3383
    Prev
    Next
    INDEX
    Explanations

    positive and beneficial

    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_40_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
     Eh
    0.35
     Squad
    0.34
    醂
    0.33
     Recommendations
    0.32
     establecidas
    0.32
    דר
    0.32
    roscopy
    0.32
    ivir
    0.31
     recomendaciones
    0.31
     စ
    0.31
    POSITIVE LOGITS
     friend
    0.51
     voice
    0.46
     voices
    0.46
    friend
    0.41
     voz
    0.40
     amiga
    0.39
     ally
    0.39
    äg
    0.39
    voice
    0.38
     FRIEND
    0.38
    Activations Density 0.151%

    No Known Activations