© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6608
    Prev
    Next
    INDEX
    Explanations

    the string "sub"

    oai_token-act-pair · gemini-2.0-flash

    sub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    sidemargin
    -0.92
    SequentialGroup
    -0.90
     '\\;'
    -0.89
     "..\..\
    -0.83
     ainfi
    -0.81
     avoient
    -0.80
    EDEFAULT
    -0.75
     GenerationType
    -0.75
     colorés
    -0.74
     cappuccio
    -0.74
    POSITIVE LOGITS
     and
    0.61
    s
    0.59
     B
    0.58
    songwriter
    0.52
    Autoritní
    0.51
    vician
    0.50
     conversation
    0.50
     сожалению
    0.49
     the
    0.48
    исленность
    0.48
    Activations Density 0.488%

    No Known Activations