INDEX

Explanations

code snippets, especially C++ and Pascal

oai_token-act-pair · gemini-2.0-flash

code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

coroutines

-0.48

WritableDatabase

-0.46

ükü

-0.46

ParallelGroup

-0.44

 millioner

-0.44

 statunit

-0.43

 HasFactory

-0.43

DataBind

-0.43

dataTables

-0.43

 repeat

-0.42

POSITIVE LOGITS

awtextra

0.65

'{@

0.59

komna

0.56

 tartalomajánló

0.55

spun

0.55

miyorum

0.54

ORETICAL

0.54

WithIOException

0.54

transQ

0.52

 Leid

0.52

Activations Density 2.394%

code snippets, especially C++ and Pascal

code snippets

No Comments

No Known Activations