© 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. 896
    Prev
    Next
    INDEX
    Explanations

    words related to programming code, relationships, legal context, and emotional reactions to circumstances

    oai_token-act-pair · gemini-2.0-flash

    say "with"

    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
     with
    -2.89
    with
    -2.41
     avec
    -2.14
    With
    -2.13
     With
    -2.09
     WITH
    -2.08
     dengan
    -1.89
     với
    -1.80
    WITH
    -1.71
    avec
    -1.64
    POSITIVE LOGITS
     nakalista
    0.61
    서는
    0.55
     versehen
    0.54
    zulegen
    0.52
    MLLoader
    0.52
    EndInit
    0.52
    __.__
    0.52
    CON
    0.49
     CON
    0.48
    isz
    0.48
    Activations Density 1.197%

    No Known Activations