© 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. 3227
    Prev
    Next
    INDEX
    Explanations

    text related to the Hare Krishna religion

    oai_token-act-pair · gemini-2.0-flash

    Hindu worship

    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
    ScopeManager
    -0.65
     ['./
    -0.64
     Nimbus
    -0.63
     comigo
    -0.63
    <>();
    -0.60
     mergeFrom
    -0.59
     *)__
    -0.58
    awakeFromNib
    -0.57
    posedge
    -0.57
    homogeneous
    -0.56
    POSITIVE LOGITS
    har
    0.49
    formas
    0.49
    bar
    0.47
    stit
    0.47
    makeConstraints
    0.47
    Desc
    0.46
     HasFactory
    0.46
     bar
    0.46
    fony
    0.45
    sti
    0.45
    Activations Density 0.390%

    No Known Activations