INDEX

Explanations

the word "give" or "gives" followed by a short pronoun

oai_token-act-pair · gemini-2.0-flash

give

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

 المعيارى

-0.76

#+#

-0.74

 متعلقه

-0.73

 mxArray

-0.71

 ErrIntOverflow

-0.64

onAttach

-0.57

yarnpkg

-0.55

ursal

-0.55

 conclusão

-0.54

HttpFoundation

-0.54

POSITIVE LOGITS

us

0.88

me

0.72

 them

0.69

you

0.67

him

0.64

 yourself

0.60

off

0.60

 myself

0.58

eux

0.52

Carriera

0.52

Activations Density 0.767%

the word "give" or "gives" followed by a short pronoun

give

No Comments

No Known Activations