INDEX

Explanations

mentions of acts, parts, steps and seasons

oai_token-act-pair · gemini-2.0-flash

Teen/decade numbers

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

itespace

-0.49

 surla

-0.44

 vandens

-0.44

 despla

-0.43

Caste

-0.43

 AssemblyTitle

-0.41

databases

-0.41

paisaje

-0.41

cyn

-0.40

cuisine

-0.40

POSITIVE LOGITS

 Fifty

1.02

 Forty

1.01

 Sixty

0.96

 Seventy

0.94

 Thirteen

0.93

 Thirty

0.92

 forty

0.92

 Ninety

0.90

 fifty

0.90

 sixty

0.89

Activations Density 8.777%

mentions of acts, parts, steps and seasons

Teen/decade numbers

No Comments

No Known Activations