© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11271
    Prev
    Next
    INDEX
    Explanations

    words related to people and their interactions

    oai_token-act-pair · gemini-2.0-flash

    programming-related syntax or terms

    np_token-act-pair-logits · gpt-4o-mini

    words ending in "ers"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    their
    -0.79
     their
    -0.68
    Their
    -0.64
    ConstraintMaker
    -0.63
     Their
    -0.62
     Leurs
    -0.60
    úgó
    -0.60
     thier
    -0.59
    bewerken
    -0.58
     Leur
    -0.57
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.70
    onAttach
    0.58
     preuves
    0.58
    ArgsConstructor
    0.57
     Référence
    0.56
    DebuggerNonUser
    0.56
    \{\\
    0.54
    RectangleBorder
    0.54
    warnai
    0.53
     oreilles
    0.53
    Activations Density 6.650%

    No Known Activations