INDEX

Explanations

words and phrases related to scientific or mathematical reasoning

oai_token-act-pair · gemini-2.0-flash

synonyms

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ätie

-0.51

odd

-0.50

DebuggerNonUser

-0.50

홀

-0.50

Hole

-0.49

ullah

-0.49

вре

-0.48

ائص

-0.48

odd

-0.48

lotten

-0.48

POSITIVE LOGITS

 equally

1.07

same

0.97

 equal

0.94

 equivalent

0.94

 Equally

0.92

Same

0.89

 same

0.89

 similarly

0.87

 identical

0.86

 stejně

0.86

Activations Density 2.546%

words and phrases related to scientific or mathematical reasoning

synonyms

No Comments

No Known Activations