© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6452
    Prev
    Next
    INDEX
    Explanations

    occurrences of someone being told something

    oai_token-act-pair · gemini-2.0-flash

    conversational text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     ControllerBase
    -0.62
    NOPQRST
    -0.57
     unto
    -0.53
     Rapids
    -0.53
     المعيارى
    -0.52
    untu
    -0.51
     Weltkrieg
    -0.51
     tep
    -0.51
    lobal
    -0.49
    ⇑
    -0.49
    POSITIVE LOGITS
    ImageContext
    0.60
     initComponents
    0.60
     législ
    0.54
    StructEnd
    0.53
     descrizione
    0.50
    IntoConstraints
    0.50
    Personensuche
    0.49
     MainAxisSize
    0.49
     ingresar
    0.48
    Transcription
    0.48
    Activations Density 1.691%

    No Known Activations