© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12179
    Prev
    Next
    INDEX
    Explanations

    clauses beginning with "that" followed by a verb or a noun

    oai_token-act-pair · gemini-2.0-flash

    say "follow"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     following
    -3.09
    following
    -3.05
     Following
    -2.83
    Following
    -2.75
     follow
    -2.69
     follows
    -2.63
     FOLLOWING
    -2.61
    follow
    -2.59
     Follow
    -2.45
    Follow
    -2.44
    POSITIVE LOGITS
    daille
    0.60
    habhar
    0.51
    ئيس
    0.48
     MotionEvent
    0.48
     AttributeSet
    0.46
    دانشنامهٔ
    0.46
     estimés
    0.46
    enni
    0.46
    اریخ
    0.45
     дописавши
    0.45
    Activations Density 5.386%

    No Known Activations