© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 600
    Prev
    Next
    INDEX
    Explanations

    words related to art and geography

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    enumi
    -0.75
    RenderAtEndOf
    -0.61
     viewDidLoad
    -0.52
    enumii
    -0.52
    SizeMode
    -0.48
     viewType
    -0.48
     doInBackground
    -0.48
     okuyayım
    -0.47
    >{@
    -0.47
    squ
    -0.46
    POSITIVE LOGITS
     ziua
    0.67
     detonation
    0.66
     дописавши
    0.63
     acidente
    0.60
    EndProject
    0.58
    AutoScaleMode
    0.58
    LookAnd
    0.57
     méda
    0.57
    AndEndTag
    0.56
     pantaloni
    0.56
    Activations Density 3.301%

    No Known Activations