© 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. 6352
    Prev
    Next
    INDEX
    Explanations

    start of code blocks or the end of code lines/blocks

    oai_token-act-pair · gemini-2.0-flash

    special character sequences or programming functions

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

    non-English code

    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
    UserScript
    -0.52
     AttributeSet
    -0.50
     חיצוניים
    -0.50
     StringField
    -0.44
     onCancelled
    -0.44
    absl
    -0.44
    halb
    -0.44
    Sucesor
    -0.43
     Glitch
    -0.43
    ốm
    -0.43
    POSITIVE LOGITS
    Espèce
    0.58
     Ouverture
    0.53
     Cataloging
    0.53
     CreateTagHelper
    0.51
    acker
    0.51
    anément
    0.51
    KURZBESCHREIBUNG
    0.49
    addCriterion
    0.49
     vermo
    0.49
     Maverick
    0.47
    Activations Density 1.338%

    No Known Activations