INDEX

Explanations

mathematical and/or chemical formulas

oai_token-act-pair · gemini-2.0-flash

brackets

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

SequentialGroup

-0.59

();)

-0.59

 فريبيس

-0.50

पया

-0.50

 lateinit

-0.50

 оригіналу

-0.50

 gratuitement

-0.50

dss

-0.50

WebVitals

-0.49

 للمعارف

-0.48

POSITIVE LOGITS

audiovisuel

0.56

 '\\;'

0.55

demik

0.54

cinoma

0.53

 sputnik

0.53

ACTERS

0.53

 OFDb

0.53

__).

0.52

)>>

0.51

ISHMENT

0.51

Activations Density 0.552%

mathematical and/or chemical formulas

brackets

No Comments

No Known Activations