INDEX

Explanations

words and symbols highly specific to code, math, and scientific publications.

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

✭✭

-0.48

 classique

-0.48

 catalytic

-0.47

ak

-0.46

 vecino

-0.46

occuper

-0.45

 mittlere

-0.43

обходимо

-0.43

=-\

-0.43

POSITIVE LOGITS

estacks

0.82

 betweenstory

0.65

parsedMessage

0.64

 externi

0.64

GenerationType

0.61

GEBURTSDATUM

0.57

kaido

0.57

tagHelperRunner

0.55

ibouti

0.54

IVEREF

0.54

Activations Density 87.659%

words and symbols highly specific to code, math, and scientific publications.

No Comments

No Known Activations