INDEX

Explanations

the word "a" or "an" around other short words.

oai_token-act-pair · gemini-2.0-flash

a

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.61

 незавершена

-0.59

 stesso

-0.56

 altri

-0.55

 acquistare

-0.55

__(/*!

-0.55

 altre

-0.54

 alternative

-0.54

ulemon

-0.53

 intermediate

-0.52

POSITIVE LOGITS

cknow

0.63

 thing

0.55

 WebApplication

0.54

таратура

0.54

 number

0.53

 '\\;'

0.53

UnknownFieldSet

0.51

TestBed

0.51

 pesar

0.50

jarat

0.50

Activations Density 0.816%

the word "a" or "an" around other short words.

a

No Comments

No Known Activations