INDEX

Explanations

words indicating certainty or strong agreement

oai_token-act-pair · gemini-2.0-flash

absolutely

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

SBATCH

-0.76

tamment

-0.76

 >=",

-0.69

 foon

-0.66

исленность

-0.64

ThroughAttribute

-0.63

setof

-0.61

MigrationBuilder

-0.61

RectangleBorder

-0.60

 كومونز

-0.60

POSITIVE LOGITS

 completely

0.79

 entirely

0.68

completely

0.66

Completely

0.66

 Completely

0.66

 utterly

0.65

 totally

0.60

 volledig

0.59

 impossible

0.58

 fully

0.56

Activations Density 1.278%

words indicating certainty or strong agreement

absolutely

No Comments

No Known Activations