© 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. 6276
    Prev
    Next
    INDEX
    Explanations

    the word 'direct' followed by a related word

    oai_token-act-pair · gemini-2.0-flash

    the term 'direct'

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

    direct

    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
    seamnă
    -0.71
    ^(@)
    -0.69
    ChildScrollView
    -0.68
     invokingState
    -0.67
    RectangleBorder
    -0.67
    WithMany
    -0.66
    PerformLayout
    -0.66
    CppCodeGen
    -0.63
    ingeki
    -0.60
    GOTREF
    -0.60
    POSITIVE LOGITS
    的她
    0.52
    aarrggbb
    0.45
    bra
    0.45
     Gaines
    0.43
     del
    0.41
     encounter
    0.41
    wired
    0.41
    prüche
    0.40
     de
    0.40
    tel
    0.40
    Activations Density 5.737%

    No Known Activations