© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4054
    Prev
    Next
    INDEX
    Explanations

    technical writing describing components, with special emphasis on words ending in -ed, to and the conditional tense

    oai_token-act-pair · gemini-2.0-flash

    turn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteAttribute
    -0.62
     normaux
    -0.59
     prêtres
    -0.58
    EndContext
    -0.53
     prêtre
    -0.52
     vectoriales
    -0.52
     gloire
    -0.52
     émissions
    -0.51
     financement
    -0.50
     couverte
    -0.50
    POSITIVE LOGITS
     turn
    0.70
    turn
    0.69
     turning
    0.66
     Turn
    0.65
     turns
    0.59
     spins
    0.59
    turning
    0.59
    Turn
    0.58
     piv
    0.57
     TURN
    0.57
    Activations Density 2.486%

    No Known Activations