© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 96
    Prev
    Next
    INDEX
    Explanations

    words and phrases having to do with depth or the past

    oai_token-act-pair · gemini-2.0-flash

    deep

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    +#+#
    -0.59
     Chwiliwch
    -0.52
    ReusableCell
    -0.51
    argout
    -0.47
    AddHtmlAttribute
    -0.47
    HasAnnotation
    -0.45
    AutoScaleMode
    -0.44
     caccia
    -0.43
    AEC
    -0.42
    onclick
    -0.42
    POSITIVE LOGITS
    
    0.64
     becauſe
    0.52
    brough
    0.52
    som
    0.52
    scription
    0.51
     OMITTED
    0.50
    MethodManager
    0.50
     cavitation
    0.50
     fubject
    0.50
    ended
    0.49
    Activations Density 9.345%

    No Known Activations