INDEX

Explanations

delimiters such as forward slashes, quotes, and parentheses

oai_token-act-pair · gemini-2.0-flash

/

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gridx

-0.56

±

-0.56

Referencoj

-0.54

gående

-0.54

astrous

-0.53

তথ্যসূত্র

-0.52

Kedves

-0.51

ercises

-0.51

脚注の使い方

-0.51

EDEFAULT

-0.50

POSITIVE LOGITS

<bos>

0.73

in

0.60

lo

0.60

con

0.57

its

0.55

has

0.54

inac

0.52

dia

0.51

any

0.51

no

0.51

Activations Density 6.849%

delimiters such as forward slashes, quotes, and parentheses

/

No Comments

No Known Activations