© 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. 5602
    Prev
    Next
    INDEX
    Explanations

    the word "into" within a specific context.

    oai_token-act-pair · gemini-2.0-flash

    tokens related to transitions or movement

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

    into

    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
     frattempo
    -0.50
    jooq
    -0.47
     confronti
    -0.47
     with
    -0.47
     terhadap
    -0.46
     for
    -0.45
    Hentet
    -0.45
    they
    -0.45
     figli
    -0.44
     recomendamos
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.79
     propOrder
    0.75
     the
    0.72
    etheless
    0.63
    Reprodução
    0.60
    — 
    0.60
    Portale
    0.60
    unately
    0.58
    PostInfinity
    0.58
     createState
    0.57
    Activations Density 7.952%

    No Known Activations