INDEX

Explanations

words used to describe, compare or qualify something as part of a scientific or technical analysis.

oai_token-act-pair · gemini-2.0-flash

hard

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

 kasarigan

-0.66

 <=",

-0.60

 Normdatei

-0.57

 архивлан

-0.52

 gainera

-0.50

NameInMap

-0.50

IntoConstraints

-0.50

 дописавши

-0.50

tawesome

-0.50

dataflow

-0.49

POSITIVE LOGITS

 hard

3.58

hard

3.16

 Hard

3.13

Hard

3.11

 HARD

2.66

HARD

2.59

 harder

2.17

 hardest

2.03

 harde

1.95

 Harder

1.70

Activations Density 12.672%

words used to describe, compare or qualify something as part of a scientific or technical analysis.

hard

No Comments

No Known Activations