INDEX

Explanations

acronyms and initialisms

oai_token-act-pair · gemini-2.0-flash

technical text

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

DockStyle

-0.84

LookAnd

-0.82



-0.77

SourceChecksum

-0.72

 NDEBUG

-0.72

bewerken

-0.71

 PLWABN

-0.71

mybatisplus

-0.69

 Shakspeare

-0.69

SBATCH

-0.69

POSITIVE LOGITS

0.61

0.48

((

0.47

 McDermott

0.45

(.

0.44

 colspan

0.43

ardless

0.43

wegian

0.43

ETIME

0.41

škai

0.41

Activations Density 6.847%

acronyms and initialisms

technical text

No Comments

No Known Activations