INDEX

Explanations

the letter T followed by a number or period

oai_token-act-pair · gemini-2.0-flash

T

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

UserScript

-0.56

AxisAlignment

-0.50

どうも

-0.50

 насељу

-0.49

Ou

-0.46

findpost

-0.45

KommentareTeilen

-0.45

ou

-0.45

verwijspagina

-0.44

OU

-0.43

POSITIVE LOGITS

المناصب

0.69

 ―――――

0.64

 تضيفلها

0.60

aarrggbb

0.59

 समीक्षाओं

0.59

 للاسماء

0.57

^(@)

0.56

ptonshire

0.55

orianCalendar

0.55

 referenties

0.55

Activations Density 0.329%

the letter T followed by a number or period

T

No Comments

No Known Activations