© 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. 6422
    Prev
    Next
    INDEX
    Explanations

    personal and corporate points of view using first person pronouns and associated verbs

    oai_token-act-pair · gemini-2.0-flash

    expresses pleasantry and/or support

    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
     typelib
    -0.75
    ніципалі
    -0.75
     transfieras
    -0.71
     дописавши
    -0.71
    TargetException
    -0.71
    setVerticalGroup
    -0.71
     nahilalakip
    -0.70
    OGND
    -0.69
    StoryboardSegue
    -0.68
    openzeppelin
    -0.68
    POSITIVE LOGITS
     be
    0.84
     are
    0.81
     estoy
    0.75
     is
    0.73
     extremely
    0.72
     very
    0.70
     sommes
    0.69
     estou
    0.68
     estamos
    0.68
     soient
    0.68
    Activations Density 0.956%

    No Known Activations