© 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. 11308
    Prev
    Next
    INDEX
    Explanations

    clauses with "to" followed by a verb, especially when negated

    oai_token-act-pair · gemini-2.0-flash

    non-English tokens or characters

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

    t

    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
     thiệu
    -0.65
     SwitchCompat
    -0.63
     AppColors
    -0.63
    adaptiveStyles
    -0.60
     engraçadas
    -0.59
    ^(@)
    -0.59
    UrlResolution
    -0.59
    IonicModule
    -0.59
    AutoScaleMode
    -0.59
     TestBed
    -0.58
    POSITIVE LOGITS
    ficado
    0.46
    EDEFAULT
    0.45
     nor
    0.44
     boxes
    0.44
     just
    0.43
    htbp
    0.43
     any
    0.42
    нский
    0.40
    '''
    0.40
    上的
    0.40
    Activations Density 3.881%

    No Known Activations