© 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. 11876
    Prev
    Next
    INDEX
    Explanations

    uses of the word "you" combined with words like "should", "will", and "need", especially in lists giving requirements.

    oai_token-act-pair · gemini-2.0-flash

    suggestions and advice

    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
     صوتيه
    -1.04
     Should
    -0.93
     Administrativna
    -0.92
    Should
    -0.90
     normaux
    -0.87
     autorytatywna
    -0.87
     prisonniers
    -0.85
     démocr
    -0.82
    should
    -0.82
     détru
    -0.82
    POSITIVE LOGITS
     Ome
    0.51
     Open
    0.49
     mf
    0.47
    Open
    0.46
     Mp
    0.46
    cm
    0.45
     Ep
    0.44
     Essay
    0.43
     Ek
    0.42
     vp
    0.41
    Activations Density 25.259%

    No Known Activations