INDEX

Explanations

a variety of different things, or has not been trained adequately

oai_token-act-pair · gemini-2.0-flash

bring

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

脚注の使い方

-0.70

Total

-0.50

HomeAsUpEnabled

-0.50

 AssemblyProduct

-0.48

 totale

-0.47

ędzy

-0.46

 textStatus

-0.45

 valueForKey

-0.45

Decided

-0.44

total

-0.44

POSITIVE LOGITS

 bringing

1.71

bringing

1.61

 brings

1.58

 Bringing

1.56

 bring

1.55

Bringing

1.52

 Bring

1.50

Bring

1.44

bring

1.39

 BRING

1.36

Activations Density 1.801%

a variety of different things, or has not been trained adequately

bring

No Comments

No Known Activations