INDEX

Explanations

scientific texts involving research methodology, models, and comparisons with existing data.

oai_token-act-pair · gemini-2.0-flash

scientific modeling

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

XmlAccessType

-0.51

Des

-0.50

WireFormatLite

-0.49

mounted

-0.48

ViewInit

-0.47

 GenerationType

-0.47

TintMode

-0.46

gro

-0.46

upsi

-0.46

lrrrr

-0.45

POSITIVE LOGITS

 kasarigan

0.70

utives

0.60

utnik

0.60

phazard

0.57

BufferException

0.55

 itſelf

0.55

avoit

0.54

 hydrostatic

0.54

 Beziehung

0.53

Kane

0.53

Activations Density 4.431%

scientific texts involving research methodology, models, and comparisons with existing data.

scientific modeling

No Comments

No Known Activations