INDEX

Explanations

complex math equations or proofs

oai_token-act-pair · gemini-2.0-flash

say "Q"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Qu

-1.65

Qu

-1.55

QU

-1.54

 Quar

-1.52

qu

-1.52

Quar

-1.49

 Quin

-1.46

CQ

-1.41

Que

-1.41

POSITIVE LOGITS

 Bergh

0.65

 Spann

0.52

 Berman

0.52

 Spicer

0.50

untergang

0.48

 désolés

0.47

rhosis

0.47

ดอก

0.46

BorderFactory

0.46

Cyfeiriadau

0.45

Activations Density 1.245%

complex math equations or proofs

say "Q"

No Comments

No Known Activations