INDEX

Explanations

words and phrases that indicate additional detail or quantity

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_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

ingt

-0.52

than

-0.50

AnimationFrame

-0.48

Glej

-0.48

IMATE

-0.47

 скоро

-0.47

rench

-0.47

InMemory

-0.46

ึก

-0.46

ern

-0.45

POSITIVE LOGITS

 سكانية

0.65

modb

0.56

 Wikiseite

0.54

 transférez

0.53

RectangleBorder

0.53

$")

0.51

IsMutable

0.50

Personensuche

0.50

cheibe

0.50

 कैसी

0.49

Activations Density 7.379%

words and phrases that indicate additional detail or quantity

more

No Comments

No Known Activations