© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 238
    Prev
    Next
    INDEX
    Explanations

    the word "into" and the word "taken" or "enter" or "go" nearby

    oai_token-act-pair · gemini-2.0-flash

    Division/Transition

    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
     into
    -2.66
    Into
    -1.98
     INTO
    -1.90
     Into
    -1.89
    into
    -1.88
    INTO
    -1.63
     vào
    -1.13
     entrado
    -0.90
     enters
    -0.80
    入
    -0.79
    POSITIVE LOGITS
     do
    0.54
    Do
    0.54
     Do
    0.47
    fertigung
    0.45
    Lähteet
    0.45
    лтемелер
    0.41
    ัน
    0.41
    posób
    0.40
    mapreduce
    0.40
     nahilalakip
    0.40
    Activations Density 0.551%

    No Known Activations