INDEX

Explanations

chemical names and formulas

oai_token-act-pair · gemini-2.0-flash

chemical/biological contexts

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

UnusedPrivate

-0.83

+:+

-0.72

GEBURTS

-0.64

="@+

-0.62

 AssemblyProduct

-0.60

ftagPool

-0.59

StoryboardSegue

-0.57

 EconPapers

-0.56

/**

-0.56

 Meksiku

-0.55

POSITIVE LOGITS

ArgsConstructor

0.57

oredCriteria

0.56

XtraGrid

0.53

 edif

0.46

 grupo

0.46

Trev

0.45

 khảo

0.45

 kred

0.45

databind

0.45

échelle

0.45

Activations Density 0.633%

chemical names and formulas

chemical/biological contexts

No Comments

No Known Activations