INDEX

Explanations

hyphens in numbers or URLs

oai_token-act-pair · gemini-2.0-flash

subtraction symbols

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 calendriers

-0.55

 onOptions

-0.52

PerformLayout

-0.52

WriteBarrier

-0.51

 DialogResult

-0.50

__()

-0.49

]='\

-0.48

Eloquent

-0.48

 protoimpl

-0.48

Rhestr

-0.47

POSITIVE LOGITS

IVEREF

0.58

 soldadura

0.48

orsese

0.48

opsis

0.45

nhof

0.44

<bos>

0.44

DockStyle

0.43

ineno

0.43

Spoljašnje

0.43

ruvate

0.42

Activations Density 0.387%

hyphens in numbers or URLs

subtraction symbols

No Comments

No Known Activations